Instructions to use maharnab/gpt2_pycode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use maharnab/gpt2_pycode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="maharnab/gpt2_pycode")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("maharnab/gpt2_pycode") model = AutoModelForCausalLM.from_pretrained("maharnab/gpt2_pycode") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use maharnab/gpt2_pycode with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maharnab/gpt2_pycode" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maharnab/gpt2_pycode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/maharnab/gpt2_pycode
- SGLang
How to use maharnab/gpt2_pycode with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "maharnab/gpt2_pycode" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maharnab/gpt2_pycode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "maharnab/gpt2_pycode" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maharnab/gpt2_pycode", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use maharnab/gpt2_pycode with Docker Model Runner:
docker model run hf.co/maharnab/gpt2_pycode
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,9 @@ datasets:
|
|
| 4 |
- flytech/python-codes-25k
|
| 5 |
tags:
|
| 6 |
- code
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
# GPT2 PyCode
|
| 9 |
|
|
@@ -51,11 +54,15 @@ Use the code below to get started with the model.
|
|
| 51 |
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
| 52 |
import re
|
| 53 |
|
| 54 |
-
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
|
| 55 |
-
model = GPT2Model.from_pretrained('gpt2')
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
input_ids = encoded_input['input_ids']
|
| 61 |
attention_mask = encoded_input['attention_mask']
|
|
|
|
| 4 |
- flytech/python-codes-25k
|
| 5 |
tags:
|
| 6 |
- code
|
| 7 |
+
language:
|
| 8 |
+
- en
|
| 9 |
+
library_name: transformers
|
| 10 |
---
|
| 11 |
# GPT2 PyCode
|
| 12 |
|
|
|
|
| 54 |
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
| 55 |
import re
|
| 56 |
|
|
|
|
|
|
|
| 57 |
|
| 58 |
+
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 59 |
+
|
| 60 |
+
tokenizer = GPT2Tokenizer.from_pretrained('maharnab/gpt2_pycode')
|
| 61 |
+
model = GPT2LMHeadModel.from_pretrained('maharnab/gpt2_pycode')
|
| 62 |
+
model.to(device)
|
| 63 |
+
|
| 64 |
+
prompt = "How to reverse a string in Python."
|
| 65 |
+
encoded_input = tokenizer.encode_plus(f"<sos><user>{prompt}</user><assistant>", max_length=20, truncation=True, return_tensors="pt").to(device)
|
| 66 |
|
| 67 |
input_ids = encoded_input['input_ids']
|
| 68 |
attention_mask = encoded_input['attention_mask']
|